3DVascNet: An Automated Software for Segmentation and Quantification of Mouse Vascular Networks in 3D.

BACKGROUND: Analysis of vascular networks is an essential step to unravel the mechanisms regulating the physiological and pathological organization of blood vessels. So far, most of the analyses are performed using 2-dimensional projections of 3-dimensional (3D) networks, a strategy that has several obvious shortcomings. For instance, it does not capture the true geometry of the vasculature and generates artifacts on vessel connectivity. These limitations are accepted in the field because manual analysis of 3D vascular networks is a laborious and complex process that is often prohibitive for large volumes. METHODS: To overcome these issues, we developed 3DVascNet, a deep learning-based software for automated segmentation and quantification of 3D retinal vascular networks. 3DVascNet performs segmentation based on a deep learning model, and it quantifies vascular morphometric parameters such as vessel density, branch length, vessel radius, and branching point density. We tested the performance of 3DVascNet using a large data set of 3D microscopy images of mouse retinal blood vessels. RESULTS: We demonstrated that 3DVascNet efficiently segments vascular networks in 3D and that vascular morphometric parameters capture phenotypes detected by using manual segmentation and quantification in 2 dimension. In addition, we showed that, despite being trained on retinal images, 3DVascNet has high generalization capability and successfully segments images originating from other data sets and organs. CONCLUSIONS: Overall, we present 3DVascNet, a freely available software that includes a user-friendly graphical interface for researchers with no programming experience, which will greatly facilitate the ability to study vascular networks in 3D in health and disease. Moreover, the source code of 3DVascNet is publicly available, thus it can be easily extended for the analysis of other 3D vascular networks by other users.

Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks.

Liquid crystal (LC)-based materials are promising platforms to develop rapid, miniaturised and low-cost gas sensor devices. In hybrid gel films containing LC droplets, characteristic optical texture variations are observed due to orientational transitions of LC molecules in the presence of distinct volatile organic compounds (VOC). Here, we investigate the use of deep convolutional neural networks (CNN) as pattern recognition systems to analyse optical textures dynamics in LC droplets exposed to a set of different VOCs. LC droplets responses to VOCs were video recorded under polarised optical microscopy (POM). CNNs were then used to extract features from the responses and, in separate tasks, to recognise and quantify the vapours exposed to the films. The impact of droplet diameter on the results was also analysed. With our classification models, we show that a single individual droplet can recognise 11 VOCs with small structural and functional differences (F1-score above 93%). The optical texture variation pattern of a droplet also reflects VOC concentration changes, as suggested by applying a regression model to acetone at 0.9-4.0% (v/v) (mean absolute errors below 0.25% (v/v)). The CNN-based methodology is thus a promising approach for VOC sensing using responses from individual LC-droplets.

Utility Serum Marker HE4 for the Differential Diagnosis Between Endometriosis and Adnexal Malignancy.

OBJECTIVE: The aim of the study was to assess the utility of serum human epididymal secretory protein E4 (HE4) biomarker in the differential diagnosis of endometriosis and adnexal malignancies. METHODS: Multicentric prospective observational study between January 2010 and December 2011 in 4 European centers (Italy, Portugal, Latvia, and Spain) was carried out. We collected 981 healthy patients diagnosed with adnexal patology and selected 65 patients diagnosed with endometriosis and analyzed their serum markers CA125, HE4, and Risk of Ovarian Malignancy Algorithm (ROMA) index. We also analyzed all cases of malignant histology and divided them according to CA125 levels (negative, ≤35 U/mL; intermediate, >35-150 U/mL; and highly positive, >150 U/mL). RESULTS: HE4 was positive only in 1.5% of cases, CA125 in 64.6%, and ROMA index in 14.1%. In the subgroup intermediate CA125 values, positive HE4 is very specific (91.2%) correctly classifying patients with benign disease, but with lower sensibility (66.1%); however, ROMA index showed a high sensibility (89.3%), with a false-positive rate of 42.8%. CONCLUSIONS: HE4 can be a very useful biomarker to exclude malignant disease in patients with endometriosis.

Self-Supervised Segmentation of 3D Fluorescence Microscopy Images Using CycleGAN.

In recent years, deep learning models have been extensively applied for the segmentation of microscopy images to efficiently and accurately quantify and characterize cells, nuclei, and other biological structures. However, typically these are supervised models that require large amounts of training data that are manually annotated to create the ground-truth. Since manual annotation of these segmentation masks is difficult and time-consuming, specially in 3D, we sought to develop a self-supervised segmentation method.Our method is based on an image-to-image translation model, the CycleGAN, which we use to learn the mapping from the fluorescence microscopy images domain to the segmentation domain. We exploit the fact that CycleGAN does not require paired data and train the model using synthetic masks, instead of manually labeled masks. These masks are created automatically based on the approximate shapes and sizes of the nuclei and Golgi, thus manual image segmentation is not needed in our proposed approach.The experimental results obtained with the proposed CycleGAN model are compared with two well-known supervised segmentation models: 3D U-Net [1] and Vox2Vox [2]. The CycleGAN model led to the following results: Dice coefficient of 78.07% for the nuclei class and 67.73% for the Golgi class with a difference of only 1.4% and 0.61% compared to the best results obtained with the supervised models Vox2Vox and 3D U-Net, respectively. Moreover, training and testing the CycleGAN model is about 5.78 times faster in comparison with the 3D U-Net model. Our results show that without manual annotation effort we can train a model that performs similarly to supervised models for the segmentation of organelles in 3D microscopy images.Clinical relevance- Segmentation of cell organelles in microscopy images is an important step to extract several features, such as the morphology, density, size, shape and texture of these organelles. These quantitative analyses provide valuable information to classify and diagnose diseases, and to study biological processes.

Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks.

Butterflies are increasingly becoming model insects where basic questions surrounding the diversity of their color patterns are being investigated. Some of these color patterns consist of simple spots and eyespots. To accelerate the pace of research surrounding these discrete and circular pattern elements we trained distinct convolutional neural networks (CNNs) for detection and measurement of butterfly spots and eyespots on digital images of butterfly wings. We compared the automatically detected and segmented spot/eyespot areas with those manually annotated. These methods were able to identify and distinguish marginal eyespots from spots, as well as distinguish these patterns from less symmetrical patches of color. In addition, the measurements of an eyespot's central area and surrounding rings were comparable with the manual measurements. These CNNs offer improvements of eyespot/spot detection and measurements relative to previous methods because it is not necessary to mathematically define the feature of interest. All that is needed is to point out the images that have those features to train the CNN.

Correction: Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks.

[This corrects the article DOI: 10.1371/journal.pone.0280998.].

Peripheral Blood Serum NMR Metabolomics Is a Powerful Tool to Discriminate Benign and Malignant Ovarian Tumors.

Ovarian cancer is the major cause of death from gynecological cancer and the third most common gynecological malignancy worldwide. Despite a slight improvement in the overall survival of ovarian carcinoma patients in recent decades, the cure rate has not improved. This is mainly due to late diagnosis and resistance to therapy. It is therefore urgent to develop effective methods for early detection and prognosis. We hypothesized that, besides being able to distinguish serum samples of patients with ovarian cancer from those of patients with benign ovarian tumors, 1H-NMR metabolomics analysis might be able to predict the malignant potential of tumors. For this, serum 1H-NMR metabolomics analyses were performed, including patients with malignant, benign and borderline ovarian tumors. The serum metabolic profiles were analyzed by multivariate statistical analysis, including principal component analysis (PCA) and orthogonal partial least squares discriminant analysis (OPLS-DA) methods. A metabolic profile associated with ovarian malignant tumors was defined, in which lactate, 3-hydroxybutyrate and acetone were increased and acetate, histidine, valine and methanol were decreased. Our data support the use of 1H-NMR metabolomics analysis as a screening method for ovarian cancer detection and might be useful for predicting the malignant potential of borderline tumors.

Curriculum learning for early Alzheimer's Disease diagnosis.

The early and asymptomatic stages of Alzheimer's Disease (AD), such as mild cognitive impairment (MCI), are hard to classify, even by experienced physicians. Deep learning approaches, such as convolutional neural networks (CNNs), have been shown to help, achieving similar or even better results. Although these methods have the advantage that features are automatically extracted from images rather than handcrafted, they do not allow for incorporating medical knowledge. In this paper we propose curriculum learning (CL) strategies for CNNs designed to diagnose healthy subjects, MCI and AD, as a way to incorporate medical knowledge to boost the performance of the networks for early AD diagnosis. CL is a training strategy of the networks that tries to mimic the way humans, in this case doctors, learn. Several CL strategies were implemented and compared to commonly used baseline methods. The results show that they improve the performance, particularly that of MCI. Clinical relevance- This work shows that the use of CL strategies improve the diagnosis of AD, particularly at an early stage.

Cross-Modal Transfer Learning Methods for Alzheimer's Disease Diagnosis.

In this paper we propose cross-modal transfer learning for Alzheimer's disease detection. We use positron emission tomography (PET) and magnetic resonance imaging (MRI) brain scans from ADNI to train convolutional neural networks (CNNs) on one modality and fine-tune it on the other modality. We start by showing that cross-modal transfer learning approaches outperform CNNs trained from scratch on a single modality. We then show that cross-modal transfer-learning also outperforms multimodal approaches using the same data.

Synthetic Generation of 3D Microscopy Images using Generative Adversarial Networks.

Fluorescence microscopy images of cell organelles enable the study of various complex biological processes. Recently, deep learning (DL) models are being used for the accurate automatic analysis of these images. DL models present state-of-the-art performance in many image analysis tasks such as object classification, segmentation and detection. However, to train a DL model a large manually annotated dataset is required. Manual annotation of 3D microscopy images is a time-consuming task and must be performed by specialists in the area. Thus, only a few images with annotations are typically available. Recent advances in generative adversarial networks (GANs) have allowed the translation of images with some conditions into realistic looking synthetic images. Therefore, in this work we explore approaches based on GANs to create synthetic 3D microscopy images. We compare four approaches that differ in the conditions of the input image. The quality of the generated images was assessed visually and using a quantitative objective GAN evaluation metric. The results showed that the GAN is able to generate synthetic images similar to the real ones. Hence, we have presented a method based on GANs to overcome the issue of small annotated datasets in the biomedical imaging field.

Unsupervised learning approach for predicting sepsis onset in ICU patients.

Sepsis is a life-threatening condition caused by a deregulated host response to infection. If not diagnosed at an early stage, septic patients can go into a septic shock, associated with aggravated patient outcomes. Research has been mostly focused on predicting sepsis onset using supervised models that require big labeled datasets to train. In this work we propose two fully unsupervised learning approaches to predict septic shock onset in the Intensive Care Unit (ICU). Our approach includes learning representations from patient multivariate timeseries using Recurrent Autoencoders. Then, we apply an anomaly detection framework, using clustering-based algorithms, on the representation space learned by the models. When evaluating the performance of the proposed approaches in the septic shock onset prediction task, the Variational Autoencoder (VAE) using Gaussian Mixture Models in the anomaly detection framework was competitive with a supervised LSTM network. Results led to an AUC of 0.82 and F1-score of 0.65 using the unsupervised approach in comparison with 0.80, 0.66 for the supervised model.Clinical relevance- This work proposes an unsupervised septic shock onset prediction framework which can improve current procedure for monitoring infection progression in the ICU.

Joint Segmentation and Pairing of Nuclei and Golgi in 3D Microscopy Images.

Blood vessels provide oxygen and nutrients to all tissues in the human body, and their incorrect organisation or dysfunction contributes to several diseases. Correct organisation of blood vessels is achieved through vascular patterning, a process that relies on endothelial cell polarization and migration against the blood flow direction. Unravelling the mechanisms governing endothelial cell polarity is essential to study the process of vascular patterning. Cell polarity is defined by a vector that goes from the nucleus centroid to the corresponding Golgi complex centroid, here defined as axial polarity. Currently, axial polarity is calculated manually, which is time-consuming and subjective. In this work, we used a deep learning approach to segment nuclei and Golgi in 3D fluorescence microscopy images of mouse retinas, and to assign nucleus-Golgi pairs. This approach predicts nuclei and Golgi segmentation masks but also a third mask corresponding to joint nuclei and Golgi segmentations. The joint segmentation mask is used to perform nucleus-Golgi pairing. We demonstrate that our deep learning approach using three masks successfully identifies nucleus-Golgi pairs, outperforming a pairing method based on a cost matrix. Our results pave the way for automated computation of axial polarity in 3D tissues and in vivo.

A machine learning approach for single cell interphase cell cycle staging.

The cell nucleus is a tightly regulated organelle and its architectural structure is dynamically orchestrated to maintain normal cell function. Indeed, fluctuations in nuclear size and shape are known to occur during the cell cycle and alterations in nuclear morphology are also hallmarks of many diseases including cancer. Regrettably, automated reliable tools for cell cycle staging at single cell level using in situ images are still limited. It is therefore urgent to establish accurate strategies combining bioimaging with high-content image analysis for a bona fide classification. In this study we developed a supervised machine learning method for interphase cell cycle staging of individual adherent cells using in situ fluorescence images of nuclei stained with DAPI. A Support Vector Machine (SVM) classifier operated over normalized nuclear features using more than 3500 DAPI stained nuclei. Molecular ground truth labels were obtained by automatic image processing using fluorescent ubiquitination-based cell cycle indicator (Fucci) technology. An average F1-Score of 87.7% was achieved with this framework. Furthermore, the method was validated on distinct cell types reaching recall values higher than 89%. Our method is a robust approach to identify cells in G1 or S/G2 at the individual level, with implications in research and clinical applications.

Combining Deep Learning with Handcrafted Features for Cell Nuclei Segmentation.

Segmentation of cell nuclei in fluorescence microscopy images provides valuable information about the shape and size of the nuclei, its chromatin texture and DNA content. It has many applications such as cell tracking, counting and classification. In this work, we extended our recently proposed approach for nuclei segmentation based on deep learning, by adding to its input handcrafted features. Our handcrafted features introduce additional domain knowledge that nuclei are expected to have an approximately round shape. For round shapes the gradient vector of points at the border point to the center. To convey this information, we compute a map of gradient convergence to be used by the CNN as a new channel, in addition to the fluorescence microscopy image. We applied our method to a dataset of microscopy images of cells stained with DAPI. Our results show that with this approach we are able to decrease the number of missdetections and, therefore, increase the F1-Score when compared to our previously proposed approach. Moreover, the results show that faster convergence is obtained when handcrafted features are combined with deep learning.

Interphase Cell Cycle Staging using Deep Learning.

The progression of cells through the cell cycle is a tightly regulated process and is known to be key in maintaining normal tissue architecture and function. Disruption of these orchestrated phases will result in alterations that can lead to many diseases including cancer. Regrettably, reliable automatic tools to evaluate the cell cycle stage of individual cells are still lacking, in particular at interphase. Therefore, the development of new tools for a proper classification are urgently needed and will be of critical importance for cancer prognosis and predictive therapeutic purposes. Thus, in this work, we aimed to investigate three deep learning approaches for interphase cell cycle staging in microscopy images: 1) joint detection and cell cycle classification of nuclei patches; 2) detection of cell nuclei patches followed by classification of the cycle stage; 3) detection and segmentation of cell nuclei followed by classification of cell cycle staging. Our methods were applied to a dataset of microscopy images of nuclei stained with DAPI. The best results (0.908 F1-Score) were obtained with approach 3 in which the segmentation step allows for an intensity normalization that takes into account the intensities of all nuclei in a given image. These results show that for a correct cell cycle staging it is important to consider the relative intensities of the nuclei. Herein, we have developed a new deep learning method for interphase cell cycle staging at single cell level with potential implications in cancer prognosis and therapeutic strategies.

Efficacy of Long-Term Oral Vitamin B12 Supplementation after Total Gastrectomy: Results from a Prospective Study.

BACKGROUND/OBJECTIVES: Vitamin B12 (VB12) deficiency is a common complication after total gastrectomy which may be associated with megaloblastic anemia and potentially irreversible neurologic symptoms. Intramuscular supplementation of VB12 has been considered the standard treatment, although it is associated with high costs and patient discomfort. PATIENTS/METHODS: We performed a prospective uncontrolled study (ACTRN12614000107628) in order to evaluate the clinical and laboratory efficacy of long-term oral VB12 supplementation in patients submitted to total gastrectomy. All patients received daily oral VB12 (1 mg/day) and were evaluated every 3 months (clinical and laboratory evaluation: hemoglobin, VB12, total iron, ferritin, and folate). RESULTS: A total of 26 patients were included with a mean age of 64 years (29-79). Patients were included with a mean period of 65 months (3-309) after total gastrectomy. At inclusion time, 17/26 patients were under intramuscular VB12, and 9 had not started supplementation yet. There were normal serum VB12 levels in 25/26 patients (mean VB12 serum levels: 657 pg/mL). The mean follow-up period was 20 (8.5-28) months. During follow-up, all patients had normal VB12 levels and there was no need for intramuscular supplementation. The patient with low VB12 levels had an increase to adequate levels, which remained stable. There were no differences with statistical significance among VB12 levels at 6 (867 pg/mL), 12 (1,008 pg/mL), 18 (1,018 pg/mL), and 24 (1,061 pg/mL) months. Iron and folate supplementation was necessary in 21 and 7 patients, respectively. CONCLUSIONS: Oral VB12 supplementation is effective and safe in patients who underwent total gastrectomy and should be considered the preferential form of supplementation.

INTRODUÇÃO: O défice de vitamina B12 (vitB12) ocorre de forma quase universal e precocemente após gastrectomia total (GT), podendo associar-se a anemia megaloblástica e alterações neurológicas potencialmente irreversíveis. A administração intramuscular de vitB12 é considerada a forma de suplementação adequada, sendo, contudo, desconfortável, dispendiosa e, atualmente, de acesso difícil. MÉTODOS/OBJETIVO: Estudo prospetivo, não controlado (ACTRN12614000107628), cujo objetivo principal foi avaliar a eficácia clínica e laboratorial a longo prazo da suplementação oral com vitB12 em doentes com GT. O objetivo secundário foi avaliar outros défices nutricionais (ferro e folatos). Os doentes foram medicados com vitB12 oral (1mg/dia) e sujeitos a avaliação clínica e laboratorial trimestral (hemoglobina, vitB12, ferro, ferritina e ácido fólico). SPSS 23 (Wilcoxon test). RESULTADOS: Incluídos 26 doentes (M-18; F-8), idade média 64 anos (29­79), com diagnósticos de adenocarcinoma (n = 25) e linfoma MALT (n = 1). Os doentes foram incluídos em média 65 meses (3­309) após GT. À data de inclusão, 17/25 doentes encontravam-se medicados com vitB12 intramuscular e 9 ainda não tinham iniciado suplementação, verificando-se níveis séricos adequados de vitB12 em 25/26 doentes (1/26 com níveis de vitB12 baixos por incumprimento da terap'utica intramuscular), sendo o valor médio de 657 pg/mL (136­1,642). Os doentes foram avaliados durante uma mediana de 23 meses (IQR 8,8). No follow-up todos os doentes apresentaram níveis normais de vitB12, não sendo necessária terap'utica intramuscular. O doente com vitB12 baixa registou um incremento para níveis adequados, que se mantiveram estáveis. Não houve diferenças com significado estatístico nos níveis de vitB12 aos 6 (867 pg/mL), 12 (1,008 pg/mL) e 24 (1,061 pg/mL) meses, embora com aumento progressivo dos mesmos. A suplementação com ferro e folatos foi necessária em 21 e 7 doentes, respetivamente. CONCLUSÃO: A suplementação oral de vitB12 é eficaz e segura em doentes com GT, pelo que esta deve ser considerada a forma preferencial de administração neste grupo de doentes.

Cysteine allows ovarian cancer cells to adapt to hypoxia and to escape from carboplatin cytotoxicity.

Ovarian cancer is the second most common gynaecologic malignancy and the main cause of death from gynaecologic cancer, due to late diagnosis and chemoresistance. Studies have reported the role of cysteine in cancer, by contributing for hydrogen sulphide (H2S) generation and as a precursor of glutathione (GSH). However, the role of cysteine in the adaptation to hypoxia and therapy response remains unclear. We used several ovarian cancer cell lines, ES2, OVCAR3, OVCAR8, A2780 and A2780cisR, to clarify cysteine relevance in ovarian cancer cells survival upon hypoxia and carboplatin. Results show that ES2 and OVCAR8 cells presented a stronger dependence on cysteine availability upon hypoxia and carboplatin exposure than OVCAR3 cells. Interestingly, the A2780 cisR, but not A2780 parental cells, benefits from cysteine upon carboplatin exposure, showing that cysteine is crucial for chemoresistance. Moreover, GSH degradation and subsequent cysteine recycling pathway is associated with ovarian cancer as seen in peripheral blood serum from patients. Higher levels of total free cysteine (Cys) and homocysteine (HCys) were found in ovarian cancer patients in comparison with benign tumours and lower levels of GSH were found in ovarian neoplasms patients in comparison with healthy individuals. Importantly, the total and S-Homocysteinylated levels distinguished blood donors from patients with neoplasms as well as patients with benign from patients with malignant tumours. The levels of S-cysteinylated proteins distinguish blood donors from patients with neoplasms and the free levels of Cys in serum distinguish blood from patients with benign tumours from patients with malignant tumours. Herein we disclosed that cysteine contributes for a worse disease prognosis, allowing faster adaptation to hypoxia and protecting cells from carboplatin. The measurement of serum cysteine levels can be an effective tool for early diagnosis, for outcome prediction and follow up of disease progression.

Atlas based sparse logistic regression for Alzheimer's Disease classification.

Sparse methods are an effective way to alleviate the curse of dimensionality in neuroimaging applications. By imposing sparsity inducing regularization terms these methods are able to perform feature selection jointly with classification.They have been used for Alzheimer's Disease (AD) and Mild cognitive impairment (MCI) classification using different approaches such as Lasso, Group Lasso and treestructured Group Lasso. The Group Lasso approaches have relied mainly on grouping contiguous voxels, either spatially or temporally. In this paper we propose two grouping approaches where feature groups are more disease related. We propose that features are grouped according to anatomically defined regions of the brain, as provided by a labeled atlas, and in a hierarchy that joins corresponding regions in the left and right hemispheres, so as to take into account the bilateral symmetry which typically occurs in AD. We apply our methods to MRI images from the ADNI and compare their performance with that of other sparse methods developed for AD. Evaluation includes classification performance and the stability of the obtained feature weights when several runs of these algorithms are performed. The proposed methods attained better or equal performance but generated more stable feature weights.